Uploaded model
- Developed by: UsernameJustAnother
- License: apache-2.0
- Finetuned from model : unsloth/Mistral-Nemo-Instruct-2407
This is an 8_0 gguf of Marlin v6. The notes for Marlin are below.
Standard disclaimer: This is me teaching myself the basics of fine-tuning, with notes extensively borrowed from https://huggingface.co./nothingiisreal/MN-12B-Celeste-V1.9
New for v6:
- Slightly different source mix. Down to 8,000 records of mostly-human convos and stories, curated by me, trained in ChatML.
- The stories have been edited to remove author's notes, and the RP chats tweaked to remove many ministrations.
- Different learning rate and back to Celeste's scaling factor setup (but Celeste trained on -base, this is -instruct).
- Now with added eval! I worked out how to get eval stats (and wandb) set up, so now I can see my failures in graphical form.
And of course yay Unsloth for letting this all train on a single A100 with variable (wildly variable) context length.
It was trained with the following settings:
model = FastLanguageModel.get_peft_model(
model,
r = 256,
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 128, # 128 / sqrt(256) gives a scaling factor of 8
lora_dropout = 0.1, # Supports any, but = 0 is optimized
bias = "none", # Supports any, but = "none" is optimized
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
random_state = 3407,
use_rslora = True, # setting the adapter scaling factor to lora_alpha/math.sqrt(r) instead of lora_alpha/r
loftq_config = None, # And LoftQ
)
lr_scheduler_kwargs = {
'min_lr': 0.0000024 # Adjust this value as needed
}
per_device_train_batch_size = 2,
per_device_eval_batch_size = 2, # defaults to 8!
gradient_accumulation_steps = 4,
eval_accumulation_steps = 4,
prediction_loss_only = True, # When performing evaluation and generating predictions, only returns the loss.
warmup_steps = 50,
num_train_epochs = 2, # For longer training runs! 12 hrs/epoch?
learning_rate = 1e-5, # 8e-5 used by Celeste, 0.0001 is from the paper, halving it. tried 5e-5, now 1e-5.
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
fp16_full_eval = True, # stops eval from trying to use fp32
eval_strategy = "steps", # 'no', 'steps', 'epoch'. Don't use this without an eval dataset etc
eval_steps = 100, # is eval_strat is set to 'steps', do every N steps.
logging_steps = 5, # so eval and logging happen on the same schedule
optim = "adamw_8bit", #
weight_decay = 0, # up from 0
lr_scheduler_type = "cosine_with_min_lr", # linear, cosine, cosine_with_min_lr, default linear
lr_scheduler_kwargs = lr_scheduler_kwargs, # needed for cosine_with_min_lr
seed = 3407,
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 1
Model tree for UsernameJustAnother/Nemo-12B-Marlin-v6-gguf
Base model
unsloth/Mistral-Nemo-Instruct-2407